Journal article icon

Journal article

Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants

Abstract:

Current public health guidelines on physical activity and sleep duration are limited by a reliance on subjective self-reported evidence. Using data from simple wrist-worn activity monitors, we developed a tailored machine learning model, using balanced random forests with Hidden Markov Models, to reliably detect a number of activity modes. We show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adul...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1038/s41598-018-26174-1

Authors


More by this author
Institution:
University of Oxford
Department:
Statistics
Role:
Author
More by this author
Institution:
University of Oxford
Department:
Statistics
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Nuffield Department of Population Health
Sub department:
Population Health
Role:
Author
National Institute of Health Research More from this funder
Li Ka Shing Foundation More from this funder
Medical Research Council More from this funder
Expand funders...
Publisher:
Nature Publishing Group Publisher's website
Journal:
Scientific Reports Journal website
Volume:
8
Article number:
7961
Publication date:
2018-05-21
Acceptance date:
2018-05-02
DOI:
EISSN:
2045-2322
Language:
English
Pubs id:
pubs:853004
UUID:
uuid:dde47b05-a0bc-428d-890d-cd3ca7e46860
Local pid:
pubs:853004
Deposit date:
2018-05-21

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP